INDEX

Explanations

references to what individuals require or need in various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Ð¼Ð¾Ñģ

-0.15

enties

-0.15

à¹Ĥà¸¢

-0.15

ertino

-0.14

openh

-0.14

 ConnectionState

-0.14

iff

-0.14

ç«ľ

-0.14

eum

-0.14

enu

-0.14

POSITIVE LOGITS

 didn

0.20

 need

0.20

 Need

0.19

Need

0.18

ned

0.18

 ever

0.17

need

0.17

Didn

0.17

æīĢ

0.17

 Didn

0.16

Activations Density 0.063%

references to what individuals require or need in various contexts

No Comments

No Known Activations